Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/mzored/init-deep/agents-mdgit clone --depth 1 https://github.com/mzored/init-deepWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01118 | $0.01118 |
| Opus 5 | $0.00559 | $0.00559 |
| Sonnet 5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
init-deep AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- init-deep CLAUDE.md — 98% identical, 7 lines differ
- init-deep GEMINI.md — 89% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Overview
Multi-platform AI documentation generator. It analyzes codebases and produces platform-native docs so AI coding assistants understand the project. Built with Python 3.11+ and the standard library only.
Setup
python3 --version # requires 3.11+
node --version # required only for markdownlint
No install step is required for local development.
Commands
# Build: regenerate all platform adapters from source/commands/init-deep
python3 scripts/build_init_deep.py
# Validate: check checked-in generated artifacts match source
python3 scripts/check_init_deep.py
python3 -m src.init_deep.cli check
# Lint/doctor source metadata
python3 -m src.init_deep.cli lint
python3 -m src.init_deep.cli doctor
# Test
python3 -m unittest discover -s tests -v
# Lint markdown
npx -y markdownlint-cli2 "README.md" "skills/**/*.md" "adapters/**/*.md" "adapters/**/*.mdc"
# Validate configs
python3 -c "from pathlib import Path; import tomllib; tomllib.loads(Path('adapters/gemini/commands/init-deep.toml').read_text(encoding='utf-8'))"
jq . .claude-plugin/plugin.json > /dev/null
jq . .claude-plugin/marketplace.json > /dev/null
jq . .codex-plugin/plugin.json > /dev/null
jq . .agents/plugins/marketplace.json > /dev/null
# Full CI locally
python3 scripts/check_init_deep.py && python3 scripts/build_init_deep.py && git diff --exit-code && python3 -m src.init_deep.cli check && python3 -m unittest discover -s tests -v
Architecture
Primary pipeline:
source/commands/init-deep/spec.toml # typed manifest: flags, metadata, intent
source/commands/init-deep/body.md # markdown workflow body
|
v
src/init_deep/manifest.py # spec.toml -> CommandSpec
src/init_deep/compiler.py # CommandSpec + body -> CommandIR
src/init_deep/targets/registry.py # registry with 9 built-in targets
src/init_deep/targets/ # target plugins: plan() + render()
|
v
src/init_deep/build.py # build_v2(): renders artifacts
scripts/build_init_deep.py # writes generated artifacts
scripts/check_init_deep.py # byte-for-byte sync validation
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 112 lines · 1,118 tokens per session scan A 68fcfd7e6e40
init-deep AGENTS.md is an instructions file published in the GitHub repository mzored/init-deep (6 stars, last pushed 2mo ago), licensed MIT. It adds 1,118 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
cladding CLAUDE.md
Instructions for qwerfunch/cladding, covering maintainer guide for ai-assisted work on cladding, spec authoring — always hash, never f-nnn, version bumps — use the script, detector additions — count is auto-recomputed and plugin manifest mirrors — built, not hand-authored.
rag-code-mcp copilot-instructions.md
Instructions for doITmagic/rag-code-mcp, covering copilot instructions - ragcode mcp, ⚖️ the golden rule, project overview, architecture & patterns and developer workflows.
pbi-context CLAUDE.md
Instructions for Osc2405/pbi-context, covering estado actual (actualizado 2026-07-15), actualización 2026-08-03 — rename pbi-docs → pbi-context, 0. contexto del proyecto (no re-investigar, ya validado), 1. feature obligatoria: soporte .pbip / tmdl and por qué es obligatoria (contexto de mercado, no opinable).
1c-ai-development-kit CLAUDE.md
Claude Code instructions for Arman-Kudaibergenov/1c-ai-development-kit, covering 1c ai workspace — claude code configuration, о проекте, структура, mandatory: mcp-first rule and when to use which mcp tool (in 1c projects).
CurrentDT-mcp CLAUDE.md
Claude Code instructions for biswajitpanday/CurrentDT-mcp, covering claude.md, project overview, development commands, development and testing.